timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Turns rough prompts into detailed, LLM-ready prompts with multiple-choice clarifying questions.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 11/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 23/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 8 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Prompt Engine。按照 https://mcp.popnx.com/i/vipul-goel-prompt-engine.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月16日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Prompt Engine,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "prompt-engine": { "command": "npx", "args": [ "-y", "prompt-engine-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Prompt Engine 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"prompt-engine": {
"command": "npx",
"args": [
"-y",
"prompt-engine-mcp"
]
}
}
}用 Prompt Engine 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Prompt Engine,或回答中出现 Prompt Engine 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Prompt Engine
Prompt Engine 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Prompt Engine,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user prompt-engine -- npx -y prompt-engine-mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Prompt Engine 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user prompt-engine -- npx -y prompt-engine-mcp应能看到 Prompt Engine 在列表中并显示已连接
用 Prompt Engine 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Prompt Engine,或回答中出现 Prompt Engine 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Prompt Engine,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "prompt-engine": { "command": "npx", "args": [ "-y", "prompt-engine-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Prompt Engine 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Prompt Engine 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Prompt Engine,或回答中出现 Prompt Engine 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Prompt Engine,按顺序:1) 用 node -v 检查是否有 Node.js。没有的话,请让我从 https://nodejs.org/en/download 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "prompt-engine": { "type": "stdio", "command": "npx", "args": [ "-y", "prompt-engine-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Prompt Engine 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
用 Prompt Engine 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Prompt Engine,或回答中出现 Prompt Engine 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user prompt-engine -- npx -y prompt-engine-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"prompt-engine": {
"command": "npx",
"args": [
"-y",
"prompt-engine-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"prompt-engine": {
"command": "npx",
"args": [
"-y",
"prompt-engine-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"prompt-engine": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prompt-engine-mcp"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 vipul-goel 验证,该账户拥有此仓库
代码最后更新于4天前
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
OSV.dev 中没有 prompt-engine-mcp@0.1.0 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月16日
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/vipul-goel-prompt-engine)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于4天前,最新版本(0.1.0)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 Prompt Engine | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
prompt-engine-mcp brings Prompt Engine to MCP clients. Prompt Engine turns a rough prompt into a detailed, LLM-ready prompt. It finds what's missing, asks you a few multiple-choice questions with a recommended answer for each, then writes the prompt and explains every addition.
The model you already use does the writing. This server supplies the method, the domain checklists, a way to ask you questions and a deterministic lint. It never calls a model or any other service, needs no API key and doesn't log prompts.
Claude Desktop. Download prompt-engine.mcpb from the latest release (not yet tested in Claude Desktop) and open it with Claude Desktop. The bundle carries its own server file, so nothing else gets installed. That file includes third-party code under the MIT, Apache-2.0 and BSD-3-Clause licenses, whose texts are in server/THIRD_PARTY_NOTICES.txt inside the bundle. To check a download, put it next to SHA256SUMS from the same release and run shasum -a 256 -c --ignore-missing SHA256SUMS (or, on Linux, sha256sum -c --ignore-missing SHA256SUMS). A good download prints the line prompt-engine.mcpb: OK; other release files in the folder get lines of their own. If there's no such line, or the bundle's line says FAILED, the file doesn't match or isn't in that folder under that name: a browser may rename a second download.
Claude Code.
claude mcp add prompt-engine -- npx -y prompt-engine-mcp
Add --scope user to use it in every project. If you also installed the Prompt Engine plugin, you don't need this server in Claude Code: the plugin's skill does the same job.
Cursor (~/.cursor/mcp.json, or .cursor/mcp.json in a project), Windsurf, Claude Desktop without the bundle and most other clients:
{
"mcpServers": { "prompt-engine": { "command": "npx", "args": ["-y", "prompt-engine-mcp"] } } }
VS Code (.vscode/mcp.json):
{
"servers": { "prompt-engine": { "type": "stdio", "command": "npx", "args": ["-y", "prompt-engine-mcp"] } } }
The server is supported on Node.js 22.19 or later. On Windows, some clients need "command": "cmd", "args": ["/c", "npx", "-y", "prompt-engine-mcp"]. To run it from a clone instead, build it (see Development and testing) and start it with node /path/to/prompt-engine/mcp/dist/cli.js; in JSON configs, that's "command": "node", "args": ["/path/to/prompt-engine/mcp/dist/cli.js"].
Ask for it in plain words: "improve this prompt: write a blog post about remote work", "quick: a Midjourney prompt for a cozy cabin at night", or "use prompt-engine on this agent prompt: …". Start with quick: to skip the questions, or with deep: for extra rounds.
What happens:
enhance_prompt and gets the method brief, then get_checklist for the prompt's domain.ask_user with its questions. Where your client supports MCP form elicitation, they appear as one form, with the recommended answers as defaults and a notes field. Otherwise, or if you close the form without answering, the model shows them as a numbered list; reply ok to accept every ★, or answer like 2b 4: your own text.The enhance prompt gives the same start from a client's prompt menu. In Claude Code, write your rough prompt first, then run /mcp__prompt-engine__enhance, optionally followed by quick, standard or deep. Claude Code passes one word per argument, so the mode is the prompt's only argument.
Every tool is annotated read-only, non-destructive, idempotent and closed-world.
| Tool | Input | Returns |
|---|---|---|
enhance_prompt | mode?: quick, standard or deep; target?: where the prompt will run, such as Midjourney | The method brief as text. It echoes the mode and target and never needs the prompt itself. |
get_checklist | domain: coding, writing, research, image-video or general | The domain's checklist with ★ defaults and an example. image-video also includes each tool's syntax. |
ask_user | questions: 1–8 of { id, header?, question, options: [{ label, description? }] (2–4), recommended, why }; intro?, notes_label?, notes_hint? (the form's message and its notes field's label and hint, in the user's language) | Structured { status, answers?, notes?, questionsText?, next }. For answered and declined, also a JSON text mirror; for ask_in_chat, one text block with the instructions and the numbered questions |
check_prompt | prompt (up to 100,000 characters); target? | Structured { heuristic, target?, targetKind, mostlyEnglish, dimensions, issues, summary }, plus a readable text version |
How ask_user asks:
| Client and connection | Result |
|---|---|
| Supports form elicitation, protocol 2026-07-28 (stdio or HTTP) | A form, through a multi-round-trip input_required result. status: "answered", each answer with source: "chosen" |
| Declared form elicitation at initialize, 2025-era protocol over stdio | A form, through an elicitation/create request |
| 2025-era protocol over HTTP | status: "ask_in_chat" with questionsText, because stateless HTTP serving can't send the client a request |
| No form support | status: "ask_in_chat" with questionsText for the model to show |
| The user declines the form | status: "declined", with the recommended answers marked source: "recommended" so they are listed as assumptions |
| The user closes the form without answering | status: "ask_in_chat" with questionsText, so the model asks in the chat instead of guessing |
| The user leaves the form open for over an hour, on a 2025-era stdio connection | The call fails (isError, "Request timed out"), and the tool description tells the model to ask the questions in its reply instead; an answer given after that doesn't reach the model |
The form has a single-choice field per question, preselected on the recommended answer, and an optional notes field of up to 1,000 characters; longer notes are cut. The only text the server adds to a form is the ★ marker and, unless the model passes intro, notes_label and notes_hint in your language, an English opening line and notes label and hint. Questions asked in the chat open with their own English line, which explains the ★, never with the form's intro or its default message; next asks the model to translate it. When a question round opens with a line of its own (the biggest gaps for a request to critique a prompt or find what's missing, that the prompt is already strong, that a pasted secret was removed, or that another person's private detail was removed), the brief has the model pass that line as intro, in 200 characters or fewer, and, when it asks in the chat, put that line before the questions' own opening line.
ask_user adds the ★ itself: it takes a ★ that stands alone at the start or end of the recommended label off, and rejects a label with any other ★, such as a star rating. A rating with one ★ on the recommended option alone, such as "4.5 ★", looks the same as that marker and loses its ★ too; the ★ that ask_user adds stands next to it. It also rejects a question, a why or a label with no visible character, and two labels in one question that differ only in whitespace, invisible characters or Unicode normalization. Joiners, variation selectors and tag characters count as differences except at the start of a label or after an ASCII character, since elsewhere they change how emoji and some scripts are drawn: the flags of England and Scotland are two labels. Labels that look alike because of letters from another script, full-width letters or ligatures are not caught. Control characters in the model's text and the user's notes become spaces (notes keep their line breaks), and unpaired surrogates become U+FFFD.
check_prompt is a heuristic. For each scored area (Clear goal, Context, Constraints, Output format, Edge cases) it reports whether the draft explicitly mentions it, with short evidence, plus lint findings from data/lint-rules.json: capitalized pressure words, requests to expose reasoning, prefill instructions, template leftovers, open [[placeholders]] and similar. It gives no score; the model scores with the shared rubric. The rule for requests to expose reasoning takes think step by step and reason step by step, with spaces or hyphens, and the phrase next to your reasoning, your thinking, by reasoning or by thinking. It can't tell such a request from a sentence where the words only meet, such as "I think step-by-step instructions would help", or where the reasoning is someone else's, such as "Help the student think step by step", and it misses other wordings, such as "think it through step by step".
The area checks, and every lint rule except the {{template}} and [[placeholder]] checks, match English text only. When a draft looks mostly non-English, an area without a match is reported as unknown rather than not found. Language is judged on the prose, without code blocks, inline code and URLs; text in bare fences, and in fences marked as text, Markdown or a prompt, counts only when the prose outside them is too short to judge. Letters of another script mark a draft as non-English once they are a fifth of its letters, so tool names don't make a Chinese draft English. An English draft that quotes a longer passage in another script, such as a sentence to translate, is read as non-English too, and its areas come back unknown. It recognizes drafts in non-Latin scripts; in German, French, Spanish, Portuguese, Italian, Dutch, Polish, Swedish, Turkish, Indonesian, Tagalog, Swahili or Romanized Hindi; and with many accented letters. Drafts in other languages, and short or terse drafts in any script, may be reported as not found.
Output format counts a format word (JSON, YAML, CSV, XML, Markdown, HTML) only in phrases such as "respond in JSON", "the output must be valid JSON", "return JSON only", or "JSON only" and "Output: JSON" at the start of a line, list item or sentence, so "build a JSON parser" doesn't count. Other wordings, such as "It must be valid JSON" or "Give me JSON only", can be reported as not found. Phrases about the task that use the same words, such as "an endpoint that returns JSON" or "stored in JSON", still count.
Lines are matched one at a time, after each control character becomes a space and each run of whitespace one space, so a lint rule about tabs or double spaces never fires here. A rule whose pattern could run slowly or miss matches is skipped and named in the summary; CONTRIBUTING.md lists the limits. The time grows linearly with the draft's length, and the tests time hostile 100,000-character drafts.
| Prompt | Argument | Returns |
|---|---|---|
enhance | mode (optional; completes to quick, standard, deep) | One user message: the method brief, then "Improve the rough prompt in my previous message, or ask me for it if there isn't one." |
| URI | Content |
|---|---|
prompt-engine://method | The method brief (what enhance_prompt returns without arguments) |
prompt-engine://output-format | The reply format, the rules for each part and the score anchors |
| `prompt-engine://qu